Humanoid Robots as Cooperative Partners for People paper by Breazeal, C., et al.. (2003) MIT Media Lab, Robotic Life Group presentation by Kósa Máté Ágoston.

Slides:



Advertisements
Similar presentations
Object Persistence for Synthetic Characters Damian Isla Bungie Studios Microsoft Corp. Bruce Blumberg Synthetic Characters MIT Media Lab.
Advertisements

ESP410 Human Movement Pedagogy 3
ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
MMAP Middle School Math Through Applications Project Dahwun Deepak Gazi Scott Sun-Young.
Activity Design Goal: work from problems and opportunities of problem domain to envision new activities.
Intelligence Give a definition of intelligence that you could defend, explaining why you believe you could defend it. Give examples of ways your definition.
University of Minho School of Engineering Centre ALGORITMI Uma Escola a Reinventar o Futuro – Semana da Escola de Engenharia - 24 a 27 de Outubro de 2011.
Chapter 10 Artificial Intelligence © 2007 Pearson Addison-Wesley. All rights reserved.
Roles of educational technology in learning
Agent Mediated Grid Services in e-Learning Chun Yan, Miao School of Computer Engineering Nanyang Technological University (NTU) Singapore April,
Constructivism Constructivism — particularly in its "social" forms — suggests that the learner is much more actively involved in a joint enterprise with.
Robots that Work in Collaboration with People Guy Hoffman and Cynthia Breazeal Robotic Life Group MIT Media Laboratory Cambridge, MA, U.S.A.
Human-robot interaction Michal de Vries. Humanoid robots as cooperative partners for people Breazeal, Brooks, Gray, Hoffman, Kidd, Lee, Lieberman, Lockerd.
Putting It all Together Facilitating Learning and Project Groups.
DED 101 Educational Psychology, Guidance And Counseling
SUNITA RAI PRINCIPAL KV AJNI
Coaching Workshop A good coach will make the players see what they can be rather than what they are. –Ara Parseghian ®
Sociable Machines Cynthia Breazeal MIT Media Lab Robotic Presence Group.
Self-Concept, Self-Esteem, Self-Efficacy, and Resilience
Noynay, Kelvin G. BSED-ENGLISH Educational Technology 1.
Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Cognitive Robots © 2014, SNU CSE Biointelligence Lab.,
Elizabeth C. Rodriguez Jessica Pettyjohn Chapter 11 Week 10.
Vygotsky: Social Learning Theory
Human Learning Aeman Alabuod. Learning Theory it is conceptual frameworks that describe how information is absorbed, processed, and retained during learning.
+ Instructional Design Models EDU 560 Fall 2012 Online Module November 13, 2012.
Evaluation: A Challenging Component of Teaching Darshana Shah, PhD. PIES
Leadership &Trust . 1.
Interstate New Teacher Assessment and Support Consortium (INTASC)
Theory (and Application) Learning: A change in human performance or performance potential that results from practice or other experience and endures over.
Knowledge and Memory: How we conceptualize information.
+ REFLECTIVE COACHING APRIL 29, Goals for Today Check in on where everyone is in our self-guided learning and practice with reflective coaching.
Instructional leadership: The role of promoting teaching and learning EMASA Conference 2011 Presentation Mathakga Botha Wits school of Education.
Human Learning Lisa Holmes. Learning Theory A learning theory is a concept that describes how learning occurs. It takes into consideration how the information.
4/12/2007dhartman, CS A Survey of Socially Interactive Robots Terrance Fong, Illah Nourbakhsh, Kerstin Dautenhahn Presentation by Dan Hartmann.
Towards Cognitive Robotics Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Christian.
Learning Science and Mathematics Concepts, Models, Representations and Talk Colleen Megowan.
THE MANAGEMENT AND CONTROL OF QUALITY, 5e, © 2002 South-Western/Thomson Learning TM 1 Chapter 5 Leadership and Strategic Planning.
Academic Needs of L2/Bilingual Learners
Aims of Workshop Introduce more effective school/University partnerships for the initial training of teachers through developing mentorship training Encourage.
Computers as Mindtools by David Jonassen Summary by David Jonassen Computers can most effectively support meaningful learning and knowledge construction.
THE DANIELSON FRAMEWORK. LEARNING TARGET I will be be able to identify to others the value of the classroom teacher, the Domains of the Danielson framework.
Human Learning Asma Marghalani.
Training and Developing a Competitive Workforce 17/04/2013.
WestEd.org Infant/Toddler Reflective Curriculum Planning Process Getting to Know Infants Through Observation.
Natural Tasking of Robots Based on Human Interaction Cues Brian Scassellati, Bryan Adams, Aaron Edsinger, Matthew Marjanovic MIT Artificial Intelligence.
LEARNER CENTERED APPROACH
Chapter 1. Cognitive Systems Introduction in Cognitive Systems, Christensen et al. Course: Robots Learning from Humans Park, Sae-Rom Lee, Woo-Jin Statistical.
1 Psychology 307: Cultural Psychology January 23 Lecture 6.
Learning Theories. Constructivism Definition: By reflecting on our experiences, we construct our own understanding of the world we live in. Learning is.
DARPA Mobile Autonomous Robot Software BAA99-09 July 1999 Natural Tasking of Robots Based on Human Interaction Cues Cynthia Breazeal Rodney Brooks Brian.
How people learn different ways to think about learning.
WP6 - D6.1 Design of integrated models ISTC-CNR September, 26/27, 2005 ISTC-CNR September, 26/27, 2005.
Click to edit Master subtitle style 3/7/10 LEADING.
+ Instructional Design Models EDU 560 Fall 2012 Online Module November 13, 2012.
TEACHING METHODS IN SCIENCES HUNGARY. 2 MAIN TEACHING STYLES Direct instruction Inquiry-based learning Cooperative learning MOTIVATION CLASSROOM MANAGEMENT.
Students need many abilities to succeed in school. It has been estimated that as much as 80% of the learning a child does is visual. Reading, using computers.
Developmentally Appropriate Practices. Five Guidelines For Developmentally Appropriate Practices.
Welcome! Please arrange yourselves in groups of 6 so that group members represent: A mix of grade levels A mix of schools 1.
Activity Design Goal: work from problems and opportunities of problem domain to envision new activities.
Functionality of objects through observation and Interaction Ruzena Bajcsy based on Luca Bogoni’s Ph.D thesis April 2016.
1 Design and evaluation methods: Objectives n Design life cycle: HF input and neglect n Levels of system design: Going beyond the interface n Sources of.
Chapter 3 Intercultural Communication Competence
Shared Intentionality
Lesson 3: The Roles of Technology
OSEP Leadership Conference July 28, 2015 Margaret Heritage, WestEd
Chapter 11: Artificial Intelligence
Understanding a Skills-Based Approach
The Intentional teacher
LEARNER-CENTERED PSYCHOLOGICAL PRINCIPLES. The American Psychological Association put together the Leaner-Centered Psychological Principles. These psychological.
Presentation transcript:

Humanoid Robots as Cooperative Partners for People paper by Breazeal, C., et al.. (2003) MIT Media Lab, Robotic Life Group presentation by Kósa Máté Ágoston cognitive Rijksuniversiteit Groningen 2010

building socially intelligent robots important implications for how we will be able to communicate with, work with, and teach robots in the future it is a critical competence for robots that will play a useful, rewarding, and long-term role in the daily lives of people

socially intelligent robot robots that show aspects of human-like social intelligence, based on deep models of human cognition and social competence contrasted to socially evocative / receptive / situated / embedded brings research closer to the „hard” problem of artificial intelligence (in small steps…) Fong, T., Nourbakhsh, I. & Dautenhahn, K. (2002)

socially intelligent robot Why? – We anthropomorphize by default – Personality lends coherence and consistence to behavior (to know someone is to predict his actions) – Natural learning – Scalability reflects in trust and sincerity (for when it gets out of hand see Blade Runner, Ridley Scott 1982)

theory of mind Assumption: – each participant has a set of mechanisms and representations for predicting and interpreting other’s actions, emotions, beliefs, desires, and other mental states Derived models: – joint attention, representation, empathy, intersubjectivity, reason (mental states to behavior), inference, social reference etc.

Collaborative approach vs. ML supervised learning techniques – the learning algorithm has no a priori knowledge about the structure of the state and action spaces, must discover any structure that exists on its own needs data, time, relatively stable enviroment problems with generalizing hard to guide for the laic bridges machine learning with HMC

Collaborative approach vs. Humans we are innate teachers we have a well-established social signaling we have infrastructure we have an affinity towards interdisciplinarity

Social Skills reciprocal cooperation is achieved with the goal to: – help the instructor maintain a good mental model of the learner – help the learner leverage from instruction and guidance to build the appropriate task models, representations, associations, etc. test of abilities: the button task

Social Skills Communication skill Deictic reference Joint attention Mutual beliefs

Communication Conversational policies – Cohen et. al. (1990) argue that much of task- oriented dialog can be understood in terms of Joint Intention Theory – Modeled after analysis of master-novice task Turn-taking skills – Modeled after human model, very robust – Envelope displays (para-linguistic cues)

Communication Conversational policies – Cohen et. al. (1990) argue that much of task- oriented dialog can be understood in terms of Joint Intention Theory – Modeled after analysis of master-novice task Turn-taking skills – Modeled after human model, very robust – Envelope displays (para-lingvistic cues) - same goal and the same plan of execution - different abilities, tools, partial knowledge and different beliefs referring to the state of the goal - communication is necessary to mobilize the potential - same goal and the same plan of execution - different abilities, tools, partial knowledge and different beliefs referring to the state of the goal - communication is necessary to mobilize the potential

Communication Conversational policies – Cohen et. al. (1990) argue that much of task- oriented dialog can be understood in terms of Joint Intention Theory – Modeled after analysis of master-novice task Turn-taking skills – Modeled after human model, very robust – Envelope displays (para-lingvistic cues) - same goal and the same plan of execution - different abilities, tools, partial knowledge and different beliefs referring to the state of the goal - communication is necessary to mobilize the potential - same goal and the same plan of execution - different abilities, tools, partial knowledge and different beliefs referring to the state of the goal - communication is necessary to mobilize the potential Organizational markers Elaborations Clarifications Confirmations Referential elaborations Confirmations of successful identification Organizational markers Elaborations Clarifications Confirmations Referential elaborations Confirmations of successful identification

Communication Conversational policies – Cohen et. al. (1990) argue that much of task- oriented dialog can be understood in terms of Joint Intention Theory – Modeled after analysis of master-novice task Turn-taking skills – Modeled after human model, very robust – Envelope displays (para-linguistic cues)

Deictic reference Estimating gaze via estimating head-pose – pan / tilt / rotation – objects in 3D spatial map projected on gaze vector – camera on the wall (panoramic view) Pointing – background and depth map extraction – candidates fit to ellipse, then presence of pointing finger is analyzed (kurtosis) – stereo camera ceiling-mounted (bird’s eye view)

Deictic reference Estimating gaze via estimating head-pose – pan / tilt / rotation – objects in 3D spatial map projected on gaze vector – camera on the wall (panoramic view) Pointing – background and depth map extraction – candidates fit to ellipse, then presence of pointing finger is analyzed (kurtosis) – stereo camera ceiling-mounted (bird’s eye view)

Deictic reference Estimating gaze via estimating head-pose – pan / tilt / rotation – objects in 3D spatial map projected on gaze vector – camera on the wall (panoramic view) Pointing – background and depth map extraction – candidates fit to ellipse, then presence of pointing finger is analyzed (kurtosis) – stereo camera ceiling-mounted (bird’s eye view)

Joint Attention – seeing vs. attending (in baby humans 7-9 months) – referential looking (in baby humans 6-18 months) – proto-declarative pointing (in b.h months) – exploiting all these at 14 months of age (in b.h.) two entities looking at the same thing is not necessarily joint attention (necessary-not-suff) updating mutual belief with a common referent is closer to the human-human model

Joint Attention To keep in mind: – Attention focus (what gets the attention) – Referent focus (the “subject” of communication) – Saliency determines a list, not a particular object – perceptual/internal/socially cued saliency – Decay of saliency – Leonardo’s model of own foci – Leonardo’s model of instructor’s foci

Beliefs – humans around the age of 3 note difference between perception and belief temporal integration of perceptual input (composite instances of real-world objects) percept tree > snapshot > belief. classification > data structure > create/update

Beliefs – humans around the age of 3 note difference between perception and belief temporal integration of perceptual input (composite instances of real-world objects) percept tree > snapshot > belief. classification > data structure > create/update when the robot shares a belief with a human, the belief gets labeled as “mutual belief” human’s attentional and referent focus are updated for the belief concerned when the robot shares a belief with a human, the belief gets labeled as “mutual belief” human’s attentional and referent focus are updated for the belief concerned

Learning From “internal” demonstration – telemetry suit  – robot interpolates exemplars using a dynamically weighted blend of the recorded button pressing trajectories Names of things – social cue feedback

Learning Task structure – task is either a (sub)task or an action, hierarchically organized – constraints exist as actions (currently used for sequential constraints but are expandable) – task goals are more than the sum of (sub)task goals – a goal can be either a state-change in world (attain a state) performance (just do it) Natural instruction

Performing in collaboration possible because of the goal-oriented approach (and the turn-taking implementation) communication of robot’s perceived SoW and intention leads to common ground which is the basis of joint intention/attention/planning knowledge of own abilities, negotiation of task with human importance of gestural cues during collaboration

Video time

Discussion Knowing what matters – restraining search-space by saliency – temporal cues + joint attention Knowing what to try – collaboration contrasted with imitation and experiment Knowing how to recognize success/faliure – goal types: change desired/performance, goal progress Knowing how to explore Knowing how to leverage the provided structure – experienced demonstration, mo’ generally social context